4.7 Article

Learning compliant dynamical system from human demonstrations for stable force control in unknown environments

Related references

Note: Only part of the references are listed.
Article Automation & Control Systems

Sensorless Optimal Interaction Control Exploiting Environment Stiffness Estimation

Loris Roveda et al.

Summary: This article presents a model-based approach to extend sensorless compliant controllers to force control. By estimating the stiffness and designing an optimal controller, the robot is able to perform tasks that require interaction with the environment.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2022)

Article Automation & Control Systems

An Approach for Robotic Leaning Inspired by Biomimetic Adaptive Control

Chao Zeng et al.

Summary: This article presents a novel representation model called human-like compliant movement primitives (Hl-CMPs), inspired by a biomimetic adaptive control strategy, which allows a robot to learn human-like compliant behaviors. By learning movement trajectories obtained from human demonstration, the robot can simultaneously learn impedance and force, and represent skills in a parametric manner.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Article Robotics

An Optimal Variable Impedance Control With Consideration of the Stability

Zhehao Jin et al.

Summary: This approach transfers human impedance functions to a robot using demonstration learning and the Gaussian mixture model/Gaussian mixture regression algorithm, designs a variable impedance controller, and ensures system stability by designing minimal complementary input.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

Article Automation & Control Systems

Robust Passivity-Based Dynamical Systems for Compliant Motion Adaptation

Haohui Huang et al.

Summary: This article proposes a motion planning scheme that generates compliant trajectories to track desired contacting forces during interaction. The scheme improves the dynamical system and develops a controller to ensure stability and safety. Simulations and a use case validation demonstrate the effectiveness of the proposed framework.

IEEE-ASME TRANSACTIONS ON MECHATRONICS (2022)

Article Robotics

Human-Robot Variable Impedance Skills Transfer Learning Based on Dynamic Movement Primitives

Xinbo Yu et al.

Summary: Endowing robots with human-like abilities is an important goal in robotics. This study develops a robot skill learning framework that considers both movement and impedance features, using learning from demonstration and electromyography method to achieve adaptivity in robot task execution.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

Article Robotics

Adaptive Compliant Skill Learning for Contact-Rich Manipulation With Human in the Loop

Weiyong Si et al.

Summary: It is important for robot manipulators to adapt to unexpected events and dynamic environments when dealing with physical contact-rich tasks. A novel framework combining learning from demonstration and human experience has been proposed to enhance the safety and adaptability of robot manipulation. Experimental results show that this framework can effectively improve the performance of physical contact-rich tasks and provide a potential solution for advanced interaction tasks with complex and dynamic physical properties through human correction via teleoperation.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

Article Robotics

A Hybrid Learning and Optimization Framework to Achieve Physically Interactive Tasks With Mobile Manipulators

Jianzhuang Zhao et al.

Summary: This article proposes a hybrid learning and optimization framework for mobile manipulators, which can be applied to complex and physically interactive tasks. The framework utilizes a physical interface, GMM/GMR, and quadratic programming to achieve passivity in the controlled system.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

Article Automation & Control Systems

A survey of robot manipulation in contact

Markku Suomalainen et al.

Summary: This survey presents the current status of robots performing manipulation tasks that require varying contact with the environment. Robots are increasingly able to perform tasks similar to humans, and there has been significant progress in executing contact tasks and mitigating uncertainty. Furthermore, robots have shown higher efficiency and better generalization capabilities in traditional tasks.

ROBOTICS AND AUTONOMOUS SYSTEMS (2022)

Article Robotics

Bilateral Teleoperation With Adaptive Impedance Control for Contact Tasks

Youssef Michel et al.

Summary: The letter introduces an adaptive impedance control architecture for robotic teleoperation of contact tasks, using Learning from Demonstration to learn variable stiffness control policies. The system relies solely on the on-board torque sensors of a commercial robotic manipulator and does not require additional hardware or user input. Evaluation results show that the proposed variable-stiffness approach outperforms standard constant-stiffness approaches in terms of safety and robot tracking performance.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Review Robotics

Variable Impedance Control and Learning-A Review

Fares J. Abu-Dakka et al.

FRONTIERS IN ROBOTICS AND AI (2020)

Article Robotics

Robust state dependent Riccati equation variable impedance control for robotic force-tracking tasks

Loris Roveda et al.

INTERNATIONAL JOURNAL OF INTELLIGENT ROBOTICS AND APPLICATIONS (2020)

Article Computer Science, Interdisciplinary Applications

Contact force control and vibration suppression in robotic polishing with a smart end effector

Chen Fan et al.

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING (2019)

Article Automation & Control Systems

Interface Design of a Physical Human-Robot Interaction System for Human Impedance Adaptive Skill Transfer

Chenguang Yang et al.

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING (2018)

Article Robotics

Force, Impedance, and Trajectory Learning for Contact Tooling and Haptic Identification

Yanan Li et al.

IEEE TRANSACTIONS ON ROBOTICS (2018)

Article Robotics

A Dynamical-System-Based Approach for Controlling Robotic Manipulators During Noncontact/Contact Transitions

Seyed Sina Mirrazavi Salehian et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2018)

Article Computer Science, Artificial Intelligence

Robotic assembly solution by human-in-the-loop teaching method based on real-time stiffness modulation

Luka Peternel et al.

AUTONOMOUS ROBOTS (2018)

Article Automation & Control Systems

Learning Compliant Movement Primitives Through Demonstration and Statistical Generalization

Miha Denisa et al.

IEEE-ASME TRANSACTIONS ON MECHATRONICS (2016)

Article Computer Science, Artificial Intelligence

Adaptation of manipulation skills in physical contact with the environment to reference force profiles

Fares J. Abu-Dakka et al.

AUTONOMOUS ROBOTS (2015)

Article Robotics

Coupling Movement Primitives: Interaction With the Environment and Bimanual Tasks

Andrej Gams et al.

IEEE TRANSACTIONS ON ROBOTICS (2014)

Article Computer Science, Artificial Intelligence

Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors

Auke Jan Ijspeert et al.

NEURAL COMPUTATION (2013)

Article Robotics

Tele-impedance: Teleoperation with impedance regulation using a body-machine interface

Arash Ajoudani et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2012)

Article Robotics

Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models

S. Mohammad Khansari-Zadeh et al.

IEEE TRANSACTIONS ON ROBOTICS (2011)

Article Computer Science, Cybernetics

Concurrent adaptation of force and impedance in the redundant muscle system

Keng Peng Tee et al.

BIOLOGICAL CYBERNETICS (2010)

Article Neurosciences

CNS Learns Stable, Accurate, and Efficient Movements Using a Simple Algorithm

David W. Franklin et al.

JOURNAL OF NEUROSCIENCE (2008)

Article Neurosciences

Haptic identification of surfaces as fields of force

VS Chib et al.

JOURNAL OF NEUROPHYSIOLOGY (2006)

Article Automation & Control Systems

Force tracking impedance control of robot manipulators under unknown environment

S Jung et al.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2004)